© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129316
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ»
    -0.27
     sob
    -0.26
    -ring
    -0.25
    eness
    -0.25
    æ³®
    -0.24
    åĺ¿
    -0.24
    ç§ĥ
    -0.23
    urers
    -0.23
     veg
    -0.23
     Mits
    -0.23
    POSITIVE LOGITS
    è¯Ħä»·
    0.27
    ä¼ĺç¾İ
    0.26
    Detect
    0.26
    esso
    0.26
    LOSE
    0.25
    _detected
    0.24
    åľ¨ç½ij绾ä¸Ĭ
    0.23
    åĵģ
    0.23
    .database
    0.23
    eor
    0.23
    Activations Density 0.013%

    No Known Activations